Fast Edge Detection Using Structured Forests
This provides a fast and accurate edge detector for vision applications like object detection and image segmentation, though it is incremental as it builds on existing structured learning and forest methods.
The paper tackles edge detection in vision systems by leveraging local structure in image patches within a structured learning framework using random decision forests, achieving state-of-the-art results on BSDS500 and NYU Depth datasets with real-time performance orders of magnitude faster than competitors.
Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests. Our novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated. The result is an approach that obtains realtime performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge detection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets.